Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A computer-implemented method for identifying potential tamper in a candidate document having content affected by noise, said method comprising: determining a candidate content value for each of a plurality of sub-regions of the candidate document and accessing an original content value for each of a plurality of sub-regions of a corresponding original document, said candidate and original content values being determined based on at least one characteristic of the content in the respective sub-regions; determining a distribution of the candidate content values by associating the candidate content values with the corresponding original content values; characterising the noise in the candidate document by determining an expected content value range based on the spread of a selected part of the distribution of candidate content values; and identifying candidate content values outside the expected content value range as potential tamper.
A computer program detects tampering in a digital document that has been altered or corrupted by noise. It divides the document and a pristine original version into multiple sub-regions. For each sub-region, it calculates a content value (e.g., average pixel intensity) representing a characteristic of that region. By comparing content values from the altered document against those from the original, the program generates a distribution of content values. This distribution is used to characterize the noise, determining a range of expected content values. Any sub-region content values falling outside this expected range are flagged as potential tampering.
2. A method according to claim 1 , wherein the candidate document and the original document have a protected region and the protected region is partitioned into tiles and the method is performed upon at least one of the tiles.
The tamper detection method from above is applied to a protected region within a document. Both the original and candidate documents possess this protected region. This protected region is further divided into smaller rectangular areas called "tiles." The tamper detection process, involving comparison of content values and noise characterization, is then independently applied to at least one of these tiles to identify potential tampering within that specific area.
3. A method according to claim 1 , further comprising determining from the distribution upper and lower bounds of candidate content values to define noise thresholds characterising the noise in the candidate document and to establish the expected content value range.
Expanding on the tamper detection method, the program determines upper and lower bounds from the distribution of candidate content values. These bounds define noise thresholds that characterize the noise present in the candidate document. These thresholds subsequently define the range of expected content values, where values outside the range are identified as potential tampering.
4. A method according to claim 3 , wherein the upper and lower bounds are determined using at least one of a mean and a variance of candidate content values.
In the method which defines upper and lower bounds from the distribution of candidate content values to define noise thresholds for tamper detection, those upper and lower bounds are calculated using statistical properties of the candidate content values, specifically the mean (average) and variance (spread) of those values. These properties are used to create a range within which content values are expected to fall, and anything outside that range is flagged as potential tamper.
5. A method according to claim 3 , wherein the upper and lower bounds are determined using methods that are robust to outlier candidate content values present in the distribution.
In the method which defines upper and lower bounds from the distribution of candidate content values to define noise thresholds for tamper detection, the upper and lower bounds are calculated using methods that are resistant to outliers (extreme values) within the distribution of candidate content values. This ensures that a few very high or low values do not skew the calculated noise thresholds.
6. A method according to claim 5 wherein the bounds are determined using trimmed mean and trimmed variance of the candidate content values.
In the method which defines upper and lower bounds from the distribution of candidate content values to define noise thresholds for tamper detection with outlier-resistance, the upper and lower bounds are calculated using the "trimmed mean" and "trimmed variance." Trimmed mean and variance exclude a certain percentage of the highest and lowest values from the calculation, providing robustness to outliers.
7. A method according to claim 5 , wherein the bounds are determined using a probability distribution and through setting noise thresholds on a primary mode of the distribution.
In the method which defines upper and lower bounds from the distribution of candidate content values to define noise thresholds for tamper detection with outlier-resistance, the method uses a probability distribution to model the candidate content values. Noise thresholds (upper and lower bounds) are set based on the primary (most frequent) mode of this probability distribution, effectively ignoring less frequent outlier values.
8. A method according to claim 1 , wherein the content values are mean pixel intensities of sub-regions of the respective documents.
In the tamper detection method, the "content values" used for comparison between original and candidate documents are defined as the average pixel intensities of the sub-regions within those documents. This means that each sub-region is summarized by its average brightness, and these averages are compared to detect changes indicative of tampering.
9. A method according to claim 1 , wherein the determining of the distribution comprises grouping the candidate content values according to one of: (i) original content values; (ii) spatial location; and (iii) a division of the protected region into subsections.
In the tamper detection method, the process of determining the distribution of candidate content values involves grouping these values based on one of the following criteria: (i) the corresponding original content values; (ii) the spatial location of the sub-region within the document; or (iii) a division of the protected region into subsections. This grouping allows for analyzing content value variations based on different aspects of the document.
10. A method according to claim 3 , wherein the upper and lower bounds are interpolated using regression based on specific upper and lower thresholds identified for corresponding specific original content values.
This invention relates to data processing techniques for determining upper and lower bounds of a parameter based on original content values. The problem addressed is the need for accurate interpolation of bounds to ensure reliable data analysis or system performance, particularly when dealing with variable or noisy input data. The method involves identifying specific upper and lower thresholds for corresponding original content values. These thresholds define the range within which the parameter of interest is expected to vary. Using regression analysis, the upper and lower bounds are then interpolated based on these thresholds. Regression provides a mathematical model that estimates the relationship between the original content values and the bounds, allowing for smooth and continuous interpolation across the data range. The interpolation process ensures that the derived bounds accurately reflect the underlying trends in the data, improving the precision of subsequent analyses or control operations. This approach is particularly useful in applications where precise boundary determination is critical, such as signal processing, quality control, or predictive modeling. By leveraging regression, the method adapts to variations in the original content values while maintaining consistency in the interpolated bounds.
11. A method according to claim 10 , wherein a specific upper threshold and a corresponding specific lower threshold are identified from a probability distribution of candidate content values associated with a corresponding specific original content value.
In the method which uses regression to determine upper and lower bounds for tamper detection, a specific upper threshold and a corresponding specific lower threshold are identified from a probability distribution of candidate content values that are associated with a specific original content value. This provides a means to establish bounds for each original content value.
12. A method according to claim 3 , further comprising adjusting a sensitivity of the method by at least one of: raising the upper bound and lowering the lower bound; and narrowing a separation between the upper bound and the lower bound.
In the method which defines upper and lower bounds from the distribution of candidate content values to define noise thresholds for tamper detection, the sensitivity of the method can be adjusted by either raising the upper bound and/or lowering the lower bound, which widens the acceptable range. Alternatively, the sensitivity can be adjusted by narrowing the separation between the upper and lower bounds, which tightens the acceptable range.
13. A method according to claim 1 , wherein the at least one characteristic comprises at least one of pixel intensity, pixel centre of mass, pixel intensity gradient, edge features of the document and frequency domain features.
In the tamper detection method, the "characteristic" of the content used to derive content values can be one or more of the following: pixel intensity, pixel center of mass, pixel intensity gradient, edge features of the document, and frequency domain features derived via transforms like Fourier transform.
14. A method according to claim 1 further comprising decoding original content values for the original document from an encoded representation formed on the candidate document.
The tamper detection method includes decoding original content values for the original document from an encoded representation that is physically embedded within the candidate document itself. Thus, the candidate document carries within it the data needed to identify tampering.
15. A method according to claim 14 wherein the encoded representation comprises a barcode.
In the tamper detection method where original content values are decoded from the candidate document, the encoded representation is a barcode. This allows for efficient storage and decoding of the original document's content values directly from the candidate document.
16. A method according to claim 1 , further comprising extracting information from the candidate document and using the extracted information to query a database to retrieve a representation of an original document associated with the candidate document.
The tamper detection method involves extracting information from the candidate document (e.g., a document ID, serial number) and using this extracted information to query a database. The database then retrieves a representation of the corresponding original document associated with the candidate document, which is used for comparison and tamper detection.
17. A method according to claim 10 , wherein at least one of the upper and lower bounds obtained through regression is non-linear.
In the method which uses regression to determine upper and lower bounds for tamper detection, at least one of the upper and lower bounds obtained through regression is non-linear. This allows for more complex and accurate modeling of the relationship between original content values and expected variations due to noise.
18. A method according to claim 1 , further comprising displaying the identified potential tamper in the candidate document on a display screen by: displaying the candidate document on the display screen; comparing the original document with the candidate document to determine at least two candidate regions, each determined candidate region including detected tamper of the candidate document; determining a confidence value associated with each determined candidate region, said confidence value defining the likelihood that the detected tamper in each candidate region is true tamper; and displaying on the display screen a representation of the detected tamper overlaid on the displayed candidate document whereby detected tamper in a first candidate region associated with a confidence value higher than that of a second candidate region is displayed different to the detected tamper in the second candidate region.
The tamper detection method includes displaying the identified potential tamper on a display screen. The candidate document is shown, and then compared to the original to identify candidate regions containing detected tamper. A confidence value is assigned to each candidate region indicating the likelihood of true tamper. The detected tamper is overlaid on the displayed candidate document, with tamper in higher-confidence regions displayed differently than tamper in lower-confidence regions (e.g., different colors, intensities).
19. A method according to claim 18 further comprising displaying, associated with each representation of the detected tamper, a representation of a magnitude of tamper thereby visually distinguishing the various instances of tamper.
In the tamper detection display method, each instance of displayed tamper is associated with a visual representation of the magnitude of the tamper. This allows a user to visually distinguish between different instances of tamper based on their severity or extent of change.
20. A method according to claim 19 wherein the representation of magnitude comprises displaying a numerical strength indicator adjacent the instance, the numeral representing an order of confidence of the tampers.
In the tamper detection display method where a representation of magnitude is displayed, the representation of magnitude is a numerical strength indicator shown next to the tamper instance. This number represents a confidence level or severity rating for the specific tamper detected.
21. A method according to claim 19 wherein the representation of magnitude comprises varying display of the candidate document at the tamper by varying at least one of colour, colour saturation, shading, flashing, outline, highlight, and background.
In the tamper detection display method where a representation of magnitude is displayed, the representation of magnitude involves varying the display of the candidate document in the tampered region. This can be achieved by altering the color, color saturation, shading, applying flashing effects, adding an outline or highlight, or changing the background appearance.
22. A method according to claim 18 , further comprising associating with the display of the candidate document a user interface permitting user traversal of the displayed candidate document through the instances of tamper.
The tamper detection display method includes a user interface that allows the user to easily navigate through the displayed candidate document, specifically jumping between the identified instances of tamper. This traversal feature facilitates a focused review of all detected tamper events.
23. A method according to claim 22 wherein the user traversal of the tampers is in an order of confidence associated with the individual instances.
In the tamper detection method that provides user traversal of tamper instances, the traversal is organized in the order of confidence associated with each individual instance. This allows the user to review the most likely or most severe instances of tamper first.
24. A computer-implemented method for identifying potential tamper in a candidate document having content affected by noise and a barcode encoding original content values of the content, said method comprising: determining a candidate content value for each of a plurality of sub-regions of the candidate document and decoding the barcode to access an original content value for each of a plurality of sub-regions of a corresponding original document, said candidate and original content values being determined based on at least one characteristic of the content in the respective sub-regions; and identifying potential tamper in at least one of the plurality of sub-regions of the candidate document based on a dynamically adjusted noise threshold, wherein the dynamically adjusted noise threshold for a first original content value is different to the dynamically adjusted noise threshold for a second different content value.
This tamper detection method is designed for documents where a barcode encodes the original content values. It calculates content values for sub-regions of the candidate document and decodes the barcode to obtain original content values for corresponding sub-regions. The core innovation lies in using a *dynamically adjusted* noise threshold to identify tamper. The noise threshold applied to a sub-region with a *first* original content value will differ from the threshold applied to a sub-region with a *second, different* original content value. This allows the system to account for variations in acceptable noise levels depending on the original image content.
25. A non-transitory computer readable storage medium having a program recorded thereon, the program being executable by computer apparatus to identify potential tamper in a candidate document having content affected by noise, said program comprising: code for determining a candidate content value for each of a plurality of sub-regions of the candidate document and accessing an original content value for each of a plurality of sub-regions of a corresponding original document, said candidate and original content values being determined based on at least one characteristic of the content in the respective sub-regions; code for determining a distribution of the candidate content values by associating the candidate content values with the corresponding original content values; code for characterising the noise in the candidate document by determining an expected content value range based on the spread of a selected part of the distribution of candidate content values; and code for identifying candidate content values outside the expected content value range as potential tamper.
This describes a non-transitory computer-readable storage medium (e.g., a hard drive, SSD, or flash drive) that stores a program. When executed by a computer, the program detects tampering in noisy digital documents. The program's functions are: calculate content values for sub-regions of the candidate and original documents; determine a distribution of the candidate content values by relating them to original values; characterize noise by finding an expected content value range based on the distribution; and finally, identify candidate content values falling outside this range as potential tamper.
26. Computer apparatus adapted to identify potential tamper in a candidate document having content affected by noise, said apparatus comprising: a processor; a display device coupled to the processor and configured to display the candidate document; and a memory coupled to the processor and storing the candidate document and a program executable by the processor, the program comprising: code for determining a candidate content value for each of a plurality of sub-regions of the candidate document and accessing an original content value for each of a plurality of sub-regions of a corresponding original document, said candidate and original content values being determined based on at least one characteristic of the content in the respective sub-regions; code for determining a distribution of the candidate content values by associating the candidate content values with the corresponding original content values; code for characterising the noise in the candidate document by determining an expected content value range based on the spread of a selected part of the distribution of candidate content values; and code for identifying, on the displayed candidate document, candidate content values outside the expected content value range as potential tamper.
This describes computer hardware (a "computer apparatus") specifically designed for tamper detection. It includes a processor, a display to show the candidate document, and memory. The memory stores a program that the processor executes. The program functions: calculate content values for sub-regions of the candidate and original documents; determine a distribution of candidate content values based on original values; characterize noise by finding an expected content value range based on that distribution; and identify and highlight on the displayed document any candidate content values falling outside the expected range, indicating potential tampering.
Unknown
September 30, 2014
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.